Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Bermejo, Sergio
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.20864
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916545894023168
author Bermejo, Sergio
author_facet Bermejo, Sergio
contents This work proposes a novel approach to enhancing annotated bibliography generation through Large Language Model (LLM) ensembles. In particular, multiple LLMs in different roles -- controllable text generation, evaluation, and summarization -- are introduced and validated using a systematic methodology to enhance model performance in scholarly tasks. Output diversity among the ensemble that generates text is obtained using different LLM parameters, followed by an LLM acting as a judge to assess relevance, accuracy, and coherence. Responses selected by several combining strategies are then merged and refined through summarization and redundancy removal techniques. The preliminary experimental validation demonstrates that the combined outputs from the LLM ensemble improve coherence and relevance compared to individual responses, leading to a 38% improvement in annotation quality and a 51% reduction in content redundancy, thus highlighting the potential for automating complex scholarly tasks while maintaining high-quality standards.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20864
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Annotated Bibliography Generation with LLM Ensembles
Bermejo, Sergio
Computation and Language
Artificial Intelligence
Machine Learning
This work proposes a novel approach to enhancing annotated bibliography generation through Large Language Model (LLM) ensembles. In particular, multiple LLMs in different roles -- controllable text generation, evaluation, and summarization -- are introduced and validated using a systematic methodology to enhance model performance in scholarly tasks. Output diversity among the ensemble that generates text is obtained using different LLM parameters, followed by an LLM acting as a judge to assess relevance, accuracy, and coherence. Responses selected by several combining strategies are then merged and refined through summarization and redundancy removal techniques. The preliminary experimental validation demonstrates that the combined outputs from the LLM ensemble improve coherence and relevance compared to individual responses, leading to a 38% improvement in annotation quality and a 51% reduction in content redundancy, thus highlighting the potential for automating complex scholarly tasks while maintaining high-quality standards.
title Enhancing Annotated Bibliography Generation with LLM Ensembles
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.20864